The present review paper provides a systematic insight into the studies published so far when it comes to the research on the cost and performance optimisation in the parcel delivery phase. Globalisation, as well as the new trends, such as selling online, directly influences the demands for the delivery of goods. Demand for the delivery of goods proportionally affects the transport prices. A great majority of deliveries is carried out in densely populated urban areas. In terms of costs, the greatest part in the courier organisations costs is observed in the technological phase of parcel delivery, which is at the same time the least efficient. For that reason, significant improvement of performance and cost optimisation in the very delivery phase is a rather challenging field for the researchers. New algorithm-based technologies, innovations in the logistics and outsourcing of individual technological phases are ways by means of which one strives to enhance the delivery efficiency, to improve performance and quality, but also - to optimise the costs in the last phase of delivery. The aim of the present paper is to offer a systematic review into the most recent research in the field of technology, innovations and outsourcing models with the aim of reducing the cost and enhancing the productivity and quality in parcel delivery.

Machine learning (ML) is a crucial component of artificial intelligence that has recently attracted attention for its application in logistics. ML algorithms are used on large datasets. They create logic correlations among given data and provide predictions of specific values. This research paper aims to conduct a systematic literature review to showcase the potential applications of machine learning in urban logistics systems, specifically focusing on enhancing satisfaction for postal logistics operators and their customers. The authors used various research publication databases in this context (Web of Science, Scopus, Google Scholar etc). The analysis of different models provides insights into diverse aspects, such as predicting product prices and types of cargo, evaluating user satisfaction, forecasting user departures, assessing optimal geographical locations for implementing postal centres, predicting purchase times before online orders, estimating delivery times in the last phase of the logistics chain and more. The significance of this research is highlighted through the identification of shortcomings in existing literature, offering guidelines for future research in developing new machine learning model for optimal operator selection. This model aims to achieve improvements in both customer and operator satisfaction simultaneously.

The active introduction and modern technologies application in the transport market greatly affect all transport branches and the ways of their business. Availability and mass usage of the internet and Web services create a new ambiance of trade through online sales and e-commerce. The increase in internet sales has a direct effect on the business of courier companies. The number of shipments in the B2C (Business-to-Consumer) segment is growing and putting an increasing pressure on costs for companies that perform pickup and delivery. Companies are trying to adapt their business to the new challenges and conditions that prevail in the transport market through different cost management models. One way to manage costs is to outsource costs. This paper proposes a model cost calculation in outsourcing services for pickup and delivery shipments based on the number of stops.